{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T08:32:33Z","timestamp":1789547553368,"version":"build-2803163510"},"reference-count":67,"publisher":"Association for Computing Machinery (ACM)","issue":"FSE","license":[{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program","award":["2023YFB4503801"],"award-info":[{"award-number":["2023YFB4503801"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102233, 62302021, 62192731, 62192730, 62072007, 62192733, 61832009"],"award-info":[{"award-number":["62102233, 62302021, 62192731, 62192730, 62072007, 62192733, 61832009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shandong Province Overseas Outstanding Youth Fund","award":["2022HWYQ-043"],"award-info":[{"award-number":["2022HWYQ-043"]}]},{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","award":["7005217,9220097,9220103,9229029,9229098,9678149"],"award-info":[{"award-number":["7005217,9220097,9220103,9229029,9229098,9678149"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Program of Hubei","award":["JD2023008"],"award-info":[{"award-number":["JD2023008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2024,7,12]]},"abstract":"<jats:p>Code translation tools, namely transpilers, are developed for automatic source-to-source translation. Latest learning-based transpilers have shown impressive enhancement against rule-based counterparts in both translation accuracy and readability, owing to their task-specific pre-training on extensive monolingual corpora. Nevertheless, their current performance still remains unsatisfactory for practical deployment, and the associated training resources are also prohibitively expensive. Large Language Models (LLMs), pre-trained on huge amounts of human-written code\/text, have shown remarkable performance in many code intelligence tasks due to their powerful generality, even without task-specific re-training\/fine-tuning. Thus, LLMs can potentially circumvent the above limitations, but they have not been exhaustively explored yet. This paper investigates diverse LLMs and learning-based transpilers for automated code translation tasks, finding that: although certain LLMs have outperformed current transpilers, they still have some accuracy issues, where most of the failures are induced by a lack of comprehension of source programs (38.51%), missing clear instructions on I\/O types in translation (14.94%), and ignoring discrepancies between source and target programs (41.38%).<\/jats:p>\n                  <jats:p>\n                    Enlightened by the above findings, we further propose\n                    <jats:bold>UniTrans<\/jats:bold>\n                    , a Unified code Translation framework, applicable to various LLMs, for unleashing their power in this field. Specifically,\n                    <jats:bold>UniTrans<\/jats:bold>\n                    first crafts a series of test cases for target programs with the assistance of source programs. Next, it harnesses the above auto-generated test cases to augment the code translation and then evaluate their correctness via execution. Afterward,\n                    <jats:bold>UniTrans<\/jats:bold>\n                    further (iteratively) repairs incorrectly translated programs prompted by test case execution results. Extensive experiments are conducted on six settings of translation datasets between Python, Java, and C++. Three recent LLMs of diverse sizes, including GPT-3.5 and LLaMA-13B\/7B, are tested with\n                    <jats:bold>UniTrans<\/jats:bold>\n                    , and all achieve substantial improvements in terms of computational accuracy and exact match accuracy among almost all translation settings, showing the universal effectiveness of\n                    <jats:bold>UniTrans<\/jats:bold>\n                    in practice.\n                  <\/jats:p>","DOI":"10.1145\/3660778","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:22:09Z","timestamp":1720779729000},"page":"1585-1608","source":"Crossref","is-referenced-by-count":113,"title":["Exploring and Unleashing the Power of Large Language Models in Automated Code Translation"],"prefix":"10.1145","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0670-4538","authenticated-orcid":false,"given":"Zhen","family":"Yang","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3905-8133","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3718-8476","authenticated-orcid":false,"given":"Zhongxing","family":"Yu","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3803-9600","authenticated-orcid":false,"given":"Jacky Wai","family":"Keung","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5579-8852","authenticated-orcid":false,"given":"Jia","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8877-3678","authenticated-orcid":false,"given":"Shuo","family":"Liu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9832-8879","authenticated-orcid":false,"given":"Yifan","family":"Hong","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5476-6074","authenticated-orcid":false,"given":"Xiaoxue","family":"Ma","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1087-226X","authenticated-orcid":false,"given":"Zhi","family":"Jin","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5828-0186","authenticated-orcid":false,"given":"Ge","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,12]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"[n. d.]. EMMA: a free Java code coverage tool. https:\/\/emma.sourceforge.net\/. (Accessed on 05\/06\/2024)."},{"key":"e_1_3_1_3_2","unstructured":"[n. d.]. FSE-24-UniTrans. https:\/\/github.com\/yz1019117968\/FSE-24-UniTrans. (Accessed on 04\/19\/2024)."},{"key":"e_1_3_1_4_2","unstructured":"[n. d.]. GeeksforGeeks. https:\/\/www.geeksforgeeks.org\/. (Accessed on 05\/06\/2024)."},{"key":"e_1_3_1_5_2","unstructured":"[n. d.]. gotranspile\/cxgo: Tool for transpiling C to Go. https:\/\/github.com\/gotranspile\/cxgo. (Accessed on 05\/06\/2024)."},{"key":"e_1_3_1_6_2","unstructured":"[n. d.]. Hugging Face - The AI community building the future. https:\/\/huggingface.co\/. (Accessed on 05\/06\/2024)."},{"key":"e_1_3_1_7_2","unstructured":"[n. d.]. immunant\/c2rust: Migrate C code to Rust. https:\/\/github.com\/immunant\/c2rust. (Accessed on 05\/06\/2024)."},{"key":"e_1_3_1_8_2","unstructured":"[n. d.]. platform.openai.com. https:\/\/platform.openai.com\/docs\/models\/gpt-3-5. (Accessed on 05\/06\/2024)."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3559555"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3212695"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3360585"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2020.3020502"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.10397"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.03374"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.03691"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409759"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510141"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3672459"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00128"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2025113.2025179"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608134"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ase.2019.00116"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1198\/tech.2006"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10742"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.09751"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2661136.2661148"},{"issue":"1","key":"e_1_3_1_27_2","first-page":"43","article-title":"Organizational research: Determining appropriate sample size in survey research","volume":"19","author":"Kotrlik JWKJW","year":"2001","unstructured":"JWKJWKotrlik and CCHCCHiggins. 2001.Organizational research: Determining appropriate sample size in survey research. Information technology, learning, and performance journal 19, 1 (2001), 43.","journal-title":"Information technology, learning, and performance journal"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/icse.2012.6227211"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00085"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.06599"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00179"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.17780"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.17780"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00072"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.00971"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2948705"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00205"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2491411.2494584"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2015.74"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ase.2015.74"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2889160.2892661"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.13474"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ase.2015.36"},{"key":"e_1_3_1_44_2","unstructured":"OpenAI. 2023. GPT3.5. https:\/\/platform.openai.com\/docs\/guides\/gpt\/chat-completions-api. (Accessed on 09\/11\/2023)."},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/icse.2007.37"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/icst.2015.7102604"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.03511"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.06773"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.03578"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2024.3382365"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.13971"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.05617"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_16"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/1806799.1806848"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/icse48619.2023.00129"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549101"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.13246"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.14824"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/icpc52881.2021.00010"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2023.107365"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534117"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.04207"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.151"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2022.106922"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2019.2906315"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.18223"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/1806799.1806831"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3468264"}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3660778","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3660778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T08:03:02Z","timestamp":1770192182000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3660778"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,12]]},"references-count":67,"journal-issue":{"issue":"FSE","published-print":{"date-parts":[[2024,7,12]]}},"alternative-id":["10.1145\/3660778"],"URL":"https:\/\/doi.org\/10.1145\/3660778","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,12]]}}}